summaryrefslogtreecommitdiff
path: root/sys/arch
AgeCommit message (Expand)Author
2011-01-04Use pmap_uncache_page() to alter cacheability of pages in bus_dmamem_map()Miod Vallat
2011-01-04Introduce pmap_uncache_page(), created from the guts of pmap_kenter_cache()Miod Vallat
2011-01-04It is actually possible to run CoolThreads servers with a graphics console,Mark Kettenis
2011-01-04XVR-300 is boring. For starters it has a very dull looking OpenPROM logo.Mark Kettenis
2011-01-04- de-register. no binary change.Jasper Lievisse Adriaanse
2011-01-03remove unused fileAlexandr Shadchin
2011-01-03Rework backtrace code, and try to cope with variadic functions betterMiod Vallat
2011-01-02More changes to pacify the Solaris virtual disk client. ImplementMark Kettenis
2011-01-02Make need_resched() call cpu_unidle() such that we wake up a process running onMark Kettenis
2011-01-02Figure out how much L2 cache is available on 88410-blessed designs, andMiod Vallat
2011-01-02Enable udl(4) on hppa, together with rasops and rawkbd for Xorg.Matthieu Herrb
2011-01-02Kill pmap_table_t typedef.Miod Vallat
2011-01-02Fix dump to work with PMAP_DIRECT, as done on mvme88k.Miod Vallat
2011-01-02Only store bus/dev/func numbers when the corresponding pointer argumentJasper Lievisse Adriaanse
2011-01-02- move resettodr and inittodr to clock.c, like the other clock related functionsJasper Lievisse Adriaanse
2011-01-02We need db_machdep.h even when TRAPDEBUG is enabled.Joel Sing
2011-01-02Include files.bluetooth so that hppa64 compiles.Joel Sing
2011-01-02Move away from using fixed-sized descriptors and fill in some missing bitsMark Kettenis
2011-01-02Use the session ID passed to use by the virtual disk client, and pass backMark Kettenis
2011-01-02Declare ourselves to be a virtual disk server during the version negotiationMark Kettenis
2011-01-01Now that we __HAVE_PMAP_DIRECT, it gets easy to simply save partial cacheMiod Vallat
2011-01-01Better errata #17 handling logic. Only concerns MULTIPROCESSOR kernels.Miod Vallat
2011-01-01Corretctly return 0xffffffff for the returned LBA if the disk is too largeMark Kettenis
2011-01-01Implement READ CAPACITY (16).Mark Kettenis
2011-01-01Move setting cpu_hzticks to the clock initialization function, likeJasper Lievisse Adriaanse
2011-01-01- ansifyJasper Lievisse Adriaanse
2011-01-01Fix horribly broken softintr_establish(). The old code was not managing theMark Kettenis
2011-01-01Only store bus/dev/func numbers when the corresponding pointer argumentMark Kettenis
2011-01-01Only store bus/dev/func numbers when the corresponding pointer argumentMark Kettenis
2010-12-31Massive overhauling of the m88k pmap, though I can't pretend it's a new pmapMiod Vallat
2010-12-31Handle writethrough mappings (as opposed to writeback) better:Miod Vallat
2010-12-31Yet another rework of the cache flushing routines. Fixes some bugs, probablyMiod Vallat
2010-12-31Introduce a new cmmu routine, for page writebacks without invalidate. Will beMiod Vallat
2010-12-31Standardize cache handling functions and defines to use wb/wbinv/inv insteadMiod Vallat
2010-12-31In db_write_bytes(), cope with memory addresses mapped by the two hardwiredMiod Vallat
2010-12-31Provide a lint-friendly __va_copy(), as done on all other platforms.Miod Vallat
2010-12-30If genassym fails, sort on the pipeline will indicate no error resultingTheo de Raadt
2010-12-30Since we save the interrupt mask in the trapframe when we get a trap, weMark Kettenis
2010-12-30Prior to loading the FPU context onto the current CPU, check to see if theJoel Sing
2010-12-30Turn signotify() into a function that also calls cpu_unidle().Joel Sing
2010-12-30Implement cpu_unidle() for MP kernels.Joel Sing
2010-12-30add a simple __va_copy inside ifdef lint, from tim van der molen.Ted Unangst
2010-12-29Bus clock doesn't matter on the Xeon 3600/5600 and Xeon 6500/7500, so don'tMark Kettenis
2010-12-28Previous diff had a buglet, found the hard way by pea@Miod Vallat
2010-12-27Correct x86_atomic_*_ul() to operate on 64bit integers, eliminatePhilip Guenthe
2010-12-27Eliminate x86_multicast_ipi() as unused and broken (doesn't handle #cpu>32).Philip Guenthe
2010-12-27Do not issue a cache maintainance operation until the last one is notMiod Vallat
2010-12-27Properly initialize MXCSR and XMM registers if we only write the x87 FPU stateMark Kettenis
2010-12-26Misplaced splx() in pmap_unsetbit().Miod Vallat
2010-12-26Kill pmap_phys_address(), and force every driver's mmap() routine to returnMiod Vallat